Example of LSTMCell usage in MXNet

Asked Apr 15 '22 at 22:52

Active Apr 15 '22 at 22:52

Viewed 37 times

I'm trying to make use of LSTM Cell, according to this tutorial: https://mxnet.apache.org/versions/1.2.1/api/python/gluon/rnn.html

model = mx.gluon.rnn.SequentialRNNCell()
model.add(mx.gluon.rnn.LSTMCell(20))
model.add(mx.gluon.rnn.LSTMCell(20))
states = model.begin_state(batch_size=32)
input = mx.nd.random.uniform(shape=(32, 10))
model.initialize()
model(input, states)

I'm getting the following error: ValueError: Deferred initialization failed because shape cannot be inferred. Operator FullyConnected registered in backend is known as FullyConnected in Python. This is a legacy operator which can only accept legacy ndarrays, while received an MXNet numpy ndarray. Please call as_nd_ndarray() upon the numpy ndarray to convert it to a legacy ndarray, and then feed the converted array to this operator.

What's wrong with it? I'm using MXnet '2.0.0' and can't find any up to date tutorial.

asked Apr 15 '22 at 22:52

Anonymous

4,692
8
61
91

It seems to be a bug in 2.0.0, it's calling hybrid_forward, which is not implemented for rnn. – Anonymous Apr 16 '22 at 19:45
2.0.0b20201108 version particularly. Worked in 2.0.0b20200720. – Anonymous Apr 16 '22 at 20:15

Example of LSTMCell usage in MXNet

0 Answers0